完成 LLAISYS 作业 1–4,支持 CPU、NVIDIA CUDA 与 天数BI-V150 - #62
Open
KevinQing17 wants to merge 4 commits into
Open
Conversation
Implement Tensor operations, CPU operators, Qwen2 inference, CUDA/CoreX backends, and validation tests. Source attribution: Portions of the CUDA runtime, GPU operators, and related CPU/interface/test code are based on public upstream PR wooway777#27 at commit 170a845; Tensor, Qwen2, numerical, interface, and validation fixes were made in this branch.
Replace runtime, operator, bindings, and CUDA/CoreX build implementations while preserving the existing test suite. Add manual GitHub Actions dispatch support.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
本次提交完成了作业 1–4,主要包括:
支持平台
平台 工具链 状态
Linux CPU GCC / Xmake Release Runtime、Tensor、8 个算子、Tiny Qwen2 以及真实 1.5B 模型推理均通过
NVIDIA RTX 4090 CUDA 13.2 / compute 8.9 完整构建、全部测试以及真实 1.5B 模型推理均通过
Iluvatar BI-V150 CoreX 4.4.0 完整构建、全部测试以及真实 1.5B 模型推理均通过
在 CPU 和两种 GPU 平台上,DeepSeek-R1-Distill-Qwen-1.5B 生成的 128-token 序列均与 Hugging Face 参考实现完全一致。
在验证环境中,CPU 后端完成 LLAISYS 推理生成耗时为 454.33 秒。
CI
GitHub Actions 已通过 Ubuntu 和 Windows Server 2022 的 Release 构建任务:
https://github.com/KevinQing17/llaisys-26s/actions/runs/31520743364
Validation notes